> ## Documentation Index > Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt > Use this file to discover all available pages before exploring further. # List Metrics > metrics_list: List quality metrics (LLM-judge prompts, custom code, or predefined metrics) used to evaluate AI voice agents. Filter by `agent_id` or `project_id` to scope results. Filtering behavior: - If only agent_id is provided: Returns metrics associated with that agent only - If only project_id is provided: Returns metrics associated with that project only - If both agent_id and project_id are provided: Returns metrics from both the agent and the project - If agents is provided: Returns metrics where any of the specified agents are in the M2M agents field - If slug is provided: Returns the metric with that specific slug Performance tip: `agent_id` (when a specific agent is in context) or `project_id` will narrow the result. Orgs can accumulate hundreds of metrics so a filter usually helps. ## OpenAPI ````yaml get /test_framework/v1/metrics/ openapi: 3.1.0 info: title: Cekura API version: v1 description: >- Complete API documentation for the Cekura platform. This API provides endpoints for testing, observing, and evaluating AI voice agents — including managing agents, running evaluators, defining metrics, and analyzing call quality. servers: - url: https://api.cekura.ai security: [] paths: /test_framework/v1/metrics/: get: tags: - test_framework summary: List metrics description: >- metrics_list: List quality metrics (LLM-judge prompts, custom code, or predefined metrics) used to evaluate AI voice agents. Filter by `agent_id` or `project_id` to scope results. Filtering behavior: - If only agent_id is provided: Returns metrics associated with that agent only - If only project_id is provided: Returns metrics associated with that project only - If both agent_id and project_id are provided: Returns metrics from both the agent and the project - If agents is provided: Returns metrics where any of the specified agents are in the M2M agents field - If slug is provided: Returns the metric with that specific slug Performance tip: `agent_id` (when a specific agent is in context) or `project_id` will narrow the result. Orgs can accumulate hundreds of metrics so a filter usually helps. operationId: metrics-list parameters: - in: query name: agent_id schema: type: integer description: | Filter by agent ID Example: `123` - in: query name: project_id schema: type: integer description: | Filter by project ID Example: `456` - in: query name: assistant_id schema: type: string description: | Filter by assistant ID Example: `asst_1234567890` - in: query name: agents schema: type: string description: > Filter metrics by agent IDs. Supports comma-separated list. Example: `1,2,3` to filter metrics associated with any of these agents - in: query name: slug schema: type: string description: | Filter by metric slug Example: `latency_metric` or `customer_satisfaction` - in: query name: filters schema: type: object description: >- JSON filter parameter for advanced filtering. Example: ```json {"operator":"and","conditions":[{"field":"agents__id","op":"in","value":[1,2,3]}]} ``` Supported fields: agents__id, eval_type, type, name Supported operators: in, eq, contains - in: query name: include_scores schema: type: boolean description: |- Include Overall and Total scores in Metric List Example: `true` or `false` responses: '200': content: application/json: schema: type: array items: $ref: '#/components/schemas/MetricList' examples: MetricList: value: - id: 123 name: description: function_name: type: basic eval_type: binary_workflow_adherence enum_values: - audio_enabled: true observability_enabled: true simulation_enabled: true prompt: evaluation_trigger: always evaluation_trigger_prompt: priority_assignment_prompt: vocera_defined_metric_code: configuration: infra_issues_timeout: key: value kb_file_ids: - knowledge_base_files: - id: agent: file_url: file_name: file_type: file_size: created_at: updated_at: metric_cost: MetricListWithOverallScore: value: - id: name: description: function_name: type: basic eval_type: binary_workflow_adherence enum_values: - audio_enabled: true observability_enabled: true simulation_enabled: true prompt: evaluation_trigger: always evaluation_trigger_prompt: priority_assignment_prompt: vocera_defined_metric_code: configuration: infra_issues_timeout: key: value kb_file_ids: - knowledge_base_files: - id: agent: file_url: file_name: file_type: file_size: created_at: updated_at: metric_cost: overall_score: total_score: description: '' security: - api_key: [] components: schemas: MetricList: type: object description: '' properties: id: type: integer readOnly: true slug: type: - string - 'null' description: >- URL-friendly unique identifier in snake_case format. Example: "customer_satisfaction_1562" maxLength: 255 project: type: - integer - 'null' agents: type: array items: type: - integer - 'null' agent_names: type: string readOnly: true name: type: string description: |- Name of the metric. Example: `"Customer Satisfaction"` or `"Appointment Booking"` maxLength: 255 description: type: string description: >- Description of what the metric measures. Example: `"Measures how satisfied customers are with the service provided"` function_name: type: - string - 'null' description: | Predefined function name Example: `"get_latency"` or `"check_critical_deviations"` maxLength: 255 type: enum: - basic - custom_prompt - custom_code - llm_judge type: string x-spec-enum-id: b44700c0a6443b40 description: >- Type of metric * `basic` - Basic (Deprecated in favor of LLM Judge) * `custom_prompt` - Custom Prompt ( Deprecated in favor of LLM Judge) * `custom_code` - Custom Code * `llm_judge` - LLM Judge eval_type: enum: - binary_workflow_adherence - binary_qualitative - continuous_qualitative - numeric - enum type: string x-spec-enum-id: 1e3e27b342bfd8ec description: |- Type of evaluation * `binary_workflow_adherence` - Binary Workflow Adherence * `binary_qualitative` - Binary Qualitative * `continuous_qualitative` - Continuous Qualitative * `numeric` - Numeric * `enum` - Enum enum_values: description: | List of possible enum values for enum type metrics. Example: `["satisfied", "unsatisfied"]` audio_enabled: type: boolean description: |- Whether this metric requires audio analysis. Example: `true` or `false` observability_enabled: type: boolean description: |- Enable this metric for observability. Example: `true` or `false` simulation_enabled: type: boolean description: |- Enable this metric for simulations. Example: `true` or `false` sampling_enabled: type: boolean description: Enable sampling for this metric using project-level sample rate prompt: type: string description: | Evaluation prompt for the metric. Example: `"Evaluate customer satisfaction based on conversation"` display_order: type: integer maximum: 2147483647 minimum: -2147483648 description: | Display order for the metric. Example: `1` evaluation_trigger: enum: - always - automatic - custom type: string description: |- * `always` - Always * `automatic` - Automatic * `custom` - Custom x-spec-enum-id: ecd3c02e0e393ef5 trigger_type: enum: - llm_judge - custom_code type: string description: |- * `llm_judge` - LLM Judge * `custom_code` - Custom Code x-spec-enum-id: 2adad4b8df61914f evaluation_trigger_prompt: type: string description: > Evaluation trigger prompt for the metric. Example: `"Evaluate metric only if call ended reason is main-agent-ended-call"` evaluation_trigger_custom_code: type: string description: > Python custom code to determine metric relevance. Code should set _result (bool) and _explanation (str). Example: ```python _result = True _explanation = "Metric is relevant" if "call_end_reason" in data and data["call_end_reason"] == "customer-hung-up": _result = False _explanation = "Customer hung up, metric not applicable" ``` priority_assignment_prompt: type: string description: | Priority assignment prompt for the metric. vocera_defined_metric_code: type: string description: | Vocera defined metric code for the metric. Example: `"7fd534f5"` maxLength: 255 configuration: description: > Custom configuration parameters for specific metrics if metric supports it. Example: - For Infrastructure issues ```json { "infra_issues_timeout": 10 } ``` kb_file_ids: type: array items: type: integer description: | List of knowledge base file IDs for the metric. Example: `[123, 456]` knowledge_base_files: type: array items: $ref: '#/components/schemas/KnowledgeBaseFile' readOnly: true scenarios: writeOnly: true description: Either "all" or a list of scenario IDs to attach to this metric custom_code: type: string writeOnly: true metric_cost: type: number format: double description: | Metric Cost Example: `0.10` readOnly: true alert_type: enum: - disabled - normal - significant_change type: string description: |- * `disabled` - Alerts Disabled * `normal` - Normal Alerts * `significant_change` - Significant Change Alerts x-spec-enum-id: 9e2661f1aeca64cf default: disabled significant_change_alert_status: enum: - enabled - disabled type: string x-spec-enum-id: 6d6f4d361b4ea1fb description: |- Alert status: enabled or disabled. * `enabled` - Enabled * `disabled` - Disabled significant_change_alert_direction: enum: - '' - increase - decrease type: string x-spec-enum-id: 1e86e60ca5cfba12 description: >- Alert direction: increase only, decrease only, or both (empty = both). Example: `"increase"`, `"decrease"`, or `"both"` * `` - Both (Increase and Decrease) * `increase` - Increase Only * `decrease` - Decrease Only window_size: type: integer readOnly: true description: | Window size for rolling statistics calculation. Example: `50` std_multiplier: type: number format: double readOnly: true description: | Standard deviation multiplier for threshold calculation. Example: `2.0` ewma_alpha: type: number format: double readOnly: true description: > Alpha value for exponentially weighted moving average (EWMA) calculation. Example: `0.1` add_to_new_agents: type: - boolean - 'null' description: >- When enabled, this metric is automatically assigned to new agents created in the project. alert_filters: oneOf: - {} - type: 'null' description: Filters to apply before computing alerts (CallLogQueryFilter format) slack_workspace: type: - integer - 'null' description: Slack workspace to send alerts to slack_channel_id: type: - string - 'null' description: Override channel ID for this metric's alerts maxLength: 255 affects_call_success: type: string readOnly: true description: > Whether this metric is configured in the project's rubric and therefore contributes to overall call success evaluation. Example: `true` uses_llm_judge: type: string readOnly: true description: > Whether this metric produces an LLM-judge narrative: a `custom_code` metric whose code delegates to the LLM judge internally. Computed server-side because the `custom_code` body is write-only and not exposed on read. Example: `true` required: - name KnowledgeBaseFile: type: object properties: id: type: integer readOnly: true agent: type: integer file: type: string format: uri writeOnly: true description: Knowledge base file pattern: (?:pdf|txt|json|csv|xml|md)$ file_url: type: string readOnly: true description: URL of the Knowledge file file_name: type: string readOnly: true description: Name of the Knowledge file file_type: type: string readOnly: true description: MIME type of the Knowledge file file_size: type: integer readOnly: true description: |- Size in bytes. Example: `1048576` created_at: type: string format: date-time readOnly: true description: |- When this record was created. Example: `2024-03-15T10:30:45Z` updated_at: type: string format: date-time readOnly: true description: |- When this record was last updated. Example: `2024-03-15T10:35:11Z` required: - agent - file securitySchemes: api_key: type: apiKey name: X-CEKURA-API-KEY in: header description: >- API Key Authentication. It should be included in the header of each request. ````